openclaw - 💡(How to fix) Fix [Bug]: Telegram session can get stuck after compaction when encrypted reasoning content fails verification

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

A Telegram direct-chat session can become stuck after a context compaction or session restore when session history replay includes encrypted reasoning content that can no longer be verified. After that, each retry in the same session fails before assistant output and returns the generic Telegram fallback message.

This may be related to #84406, but this case is not file-upload specific. It reproduces on normal text messages after a long-running Telegram session is compacted/restored.

Error Message

OpenClaw should not let one invalid encrypted reasoning payload leave the Telegram session permanently unusable. It should either sanitize/drop encrypted reasoning payloads that are unsafe to replay, or detect this specific provider error and recover with a clean checkpoint/session while giving the user a specific recovery message. The provider rejects the replayed request with an error shaped like: The user sees a transient-looking error, but retrying cannot fix it because the persisted session history is what causes the failure. /new works as a manual workaround, but the recovery should be automatic or at least explicit.

Root Cause

The user sees a transient-looking error, but retrying cannot fix it because the persisted session history is what causes the failure. /new works as a manual workaround, but the recovery should be automatic or at least explicit.

Fix Action

Fix / Workaround

The user sees a transient-looking error, but retrying cannot fix it because the persisted session history is what causes the failure. /new works as a manual workaround, but the recovery should be automatic or at least explicit.

Code Example

400 The encrypted content ... could not be verified. Reason: Encrypted content could not be decrypted or parsed.

---

Something went wrong while processing your request. Please try again, or use /new to start a fresh session.
RAW_BUFFERClick to expand / collapse

Bug type

Session recovery / Telegram integration

Summary

A Telegram direct-chat session can become stuck after a context compaction or session restore when session history replay includes encrypted reasoning content that can no longer be verified. After that, each retry in the same session fails before assistant output and returns the generic Telegram fallback message.

This may be related to #84406, but this case is not file-upload specific. It reproduces on normal text messages after a long-running Telegram session is compacted/restored.

Steps to reproduce

  1. Use a Telegram direct-chat session long enough for context compaction or session restore to occur.
  2. Send another normal text message in the same Telegram session.
  3. Observe that the model request fails before producing assistant content.
  4. Retry in the same session.

Expected behavior

OpenClaw should not let one invalid encrypted reasoning payload leave the Telegram session permanently unusable. It should either sanitize/drop encrypted reasoning payloads that are unsafe to replay, or detect this specific provider error and recover with a clean checkpoint/session while giving the user a specific recovery message.

Actual behavior

The provider rejects the replayed request with an error shaped like:

400 The encrypted content ... could not be verified. Reason: Encrypted content could not be decrypted or parsed.

OpenClaw then returns only the generic Telegram fallback:

Something went wrong while processing your request. Please try again, or use /new to start a fresh session.

Retrying the same session continues to fail until a fresh session is started.

Impact and severity

The user sees a transient-looking error, but retrying cannot fix it because the persisted session history is what causes the failure. /new works as a manual workaround, but the recovery should be automatic or at least explicit.

Additional information

No private logs are attached. The local evidence showed repeated zero-token provider failures before assistant output, followed by the Telegram delivery fallback.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

OpenClaw should not let one invalid encrypted reasoning payload leave the Telegram session permanently unusable. It should either sanitize/drop encrypted reasoning payloads that are unsafe to replay, or detect this specific provider error and recover with a clean checkpoint/session while giving the user a specific recovery message.

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix [Bug]: Telegram session can get stuck after compaction when encrypted reasoning content fails verification